INDEX

Explanations

information related to tennis tournaments and their participants

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

igot

-0.63

 Picchu

-0.50

 weld

-0.49

mazda

-0.46

Mul

-0.45

 Blount

-0.45

 grades

-0.44

 &___

-0.44

Newswire

-0.44

 plant

-0.43

POSITIVE LOGITS

 tennis

0.93

 Tennis

0.89

istoitu

0.85

tennis

0.84

Tennis

0.84

 Walkover

0.81

 initComponents

0.76

 незавершена

0.76

Datuak

0.74

ⓧ

0.72

Activations Density 0.084%

information related to tennis tournaments and their participants

No Comments

No Known Activations